[PATCH 09/32] nohz/cpuset: Restart tick when nohz flag is cleared on cpuset

[Steven Rostedt]

From: Frederic Weisbecker <fweisbec@xxxxxxxxx>

Issue an IPI to restart the tick on a CPU that belongs
to a cpuset when its nohz flag gets cleared.

Signed-off-by: Frederic Weisbecker <fweisbec@xxxxxxxxx>
Cc: Alessio Igor Bogani <abogani@xxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Avi Kivity <avi@xxxxxxxxxx>
Cc: Chris Metcalf <cmetcalf@xxxxxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxx>
Cc: Daniel Lezcano <daniel.lezcano@xxxxxxxxxx>
Cc: Geoff Levand <geoff@xxxxxxxxxxxxx>
Cc: Gilad Ben Yossef <gilad@xxxxxxxxxxxxx>
Cc: Hakan Akkan <hakanakkan@xxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Kevin Hilman <khilman@xxxxxx>
Cc: Max Krasnyansky <maxk@xxxxxxxxxxxx>
Cc: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Stephen Hemminger <shemminger@xxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Sven-Thorsten Dietrich <thebigcorporation@xxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
---
 include/linux/cpuset.h   |    2 ++
 kernel/cpuset.c          |   25 +++++++++++++++++++++++--
 kernel/time/tick-sched.c |    8 ++++++++
 3 files changed, 33 insertions(+), 2 deletions(-)

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 7e7eb41..631968b 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -260,6 +260,8 @@ static inline bool cpuset_adaptive_nohz(void)
 	 */
 	return cpuset_cpu_adaptive_nohz(smp_processor_id());
 }
+
+extern void cpuset_exit_nohz_interrupt(void *unused);
 #else
 static inline bool cpuset_cpu_adaptive_nohz(int cpu) { return false; }
 static inline bool cpuset_adaptive_nohz(void) { return false; }
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 6319d8e..1b67e5b 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1200,6 +1200,14 @@ static void cpuset_change_flag(struct task_struct *tsk,
 
 DEFINE_PER_CPU(atomic_t, cpu_adaptive_nohz_ref);
 
+static void cpu_exit_nohz(int cpu)
+{
+	preempt_disable();
+	smp_call_function_single(cpu, cpuset_exit_nohz_interrupt,
+				 NULL, true);
+	preempt_enable();
+}
+
 static void update_nohz_cpus(struct cpuset *old_cs, struct cpuset *cs)
 {
 	int cpu;
@@ -1211,9 +1219,22 @@ static void update_nohz_cpus(struct cpuset *old_cs, struct cpuset *cs)
 	for_each_cpu(cpu, cs->cpus_allowed) {
 		atomic_t *ref = &per_cpu(cpu_adaptive_nohz_ref, cpu);
 		if (is_adaptive_nohz(cs))
-			atomic_inc(ref);
+			val = atomic_inc_return(ref);
 		else
-			atomic_dec(ref);
+			val = atomic_dec_return(ref);
+
+		if (!val) {
+			/*
+			 * The update to cpu_adaptive_nohz_ref must be
+			 * visible right away. So that once we restart the tick
+			 * from the IPI, it won't be stopped again due to cache
+			 * update lag.
+			 * FIXME: We probably need more to ensure this value is really
+			 * visible right away.
+			 */
+			smp_mb();
+			cpu_exit_nohz(cpu);
+		}
 	}
 }
 #else
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 0a5e650..de7de68 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -884,6 +884,14 @@ void tick_nohz_check_adaptive(void)
 	}
 }
 
+void cpuset_exit_nohz_interrupt(void *unused)
+{
+	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+
+	if (ts->tick_stopped && !is_idle_task(current))
+		tick_nohz_restart_adaptive();
+}
+
 void tick_nohz_post_schedule(void)
 {
 	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
-- 
1.7.10.4


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/